The conditional expectation via a general class of nonlinear networks

Author

Zhu, Mang ; Cadzow, James A.

Author_Institution

Dept. of Electr. Eng., Vanderbilt Univ., Nashville, TN, USA

Volume

ii

fYear

1994

fDate

19-22 Apr 1994

Abstract

A general class of nonlinear parametric multi-layered networks is introduced. This class is a generalization of the standard neural network. The dynamic behavior of members of this class are analyzed and the popular least squared error criterion is used for judgement of goodness of model fit. The output of the network is shown to be an estimator of the conditional expectation function for the desired output under condition made on the given inputs. Multi-directional search (MDS) as a new nonlinear programming technique is discussed in the paper. Examples of the simulation results are given at the end of the paper to show the exact fit of the calculated expectation function and the output of the network. The results from back propagation and MDS are compared

Keywords

least mean squares methods; multilayer perceptrons; nonlinear programming; parameter estimation; search problems; conditional expectation; desired output; dynamic behavior; generalization; goodness of model fit; least squared error criterion; multidirectional search; nonlinear parametric multilayered networks; nonlinear programming technique; standard neural network; Neural networks; Particle measurements;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389597

Filename

389597